Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as readOnlyHint=true, so the description does not need to disclose mutation—but it adds value by listing returned data fields. However, it does not mention behavioral traits like rate limits or authentication requirements, though the API endpoint is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences: the first covers purpose and output, the second covers usage requirements. All information is front-loaded and no superfluous detail is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (11 parameters, nested objects, no output schema), the description describes the main return fields and gives a usage tip, but lacks details on error cases, auth, or comprehensive return structure. It meets the minimum but could be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 18% schema coverage, the description must compensate. It highlights the most critical parameter (device.ip_address) and suggests additional useful fields (email, billing, order). While this aids understanding, it does not explain the majority of the 11 parameters, leaving a gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'score' and the resource 'transaction for fraud risk', enumerating key output fields (risk_score, IP risk, disposition, remaining query funds). It also hints at tool differentiation by calling it 'the lightest, cheapest assessment', which sets it apart from siblings that likely provide more detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a minimal input requirement ('Send at least device.ip_address') and a suggestion for better scoring ('plus email/billing/order'), but does not explicitly state when to use this tool versus the sibling tools (minfraud_factors, minfraud_insights, minfraud_report_transaction). Usage guidance is implied but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.